* fix(ralph-loop): skip user messages in transcript completion detection (#622)
The transcript-based completion detection was searching the entire JSONL
file for <promise>DONE</promise>, including user message entries. The
RALPH_LOOP_TEMPLATE instructional text contains this literal pattern,
which gets recorded as a user message, causing false positive completion
detection on every iteration. This made the loop always terminate at
iteration 1.
Fix: Parse JSONL entries line-by-line and skip entries with type 'user'
so only tool_result/assistant entries are checked for the completion
promise. Also remove the hardcoded <promise>DONE</promise> from the
template exit conditions as defense-in-depth.
* chore: changes by sisyphus-dev-ai
---------
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
- Remove invalid Pick<Plugin> type usage
- Add explicit input/output type annotations
- Add comprehensive test suite (5 tests)
- Tests verify truncation at 30 chars with '...' suffix
When AI generates AskUserQuestion tool calls with option labels longer
than 30 characters, opencode validation rejects them with "too_big" error.
This fix adds a pre-tool-use hook that automatically truncates labels
to 30 characters (with "..." suffix) before the validation occurs.
Fixes the error:
"The question tool was called with invalid arguments: expected string
to have <=30 characters"
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add 'compaction' to DEFAULT_SKIP_AGENTS
- Skip compaction agent messages when resolving agent info
- Skip injection when compaction occurred but no real agent resolved
- Replace cooldown-based approach with agent-based filtering
The bash tool always runs in a Unix-like shell (bash/sh), even on Windows (via Git Bash, WSL, etc.), so we should always use unix export syntax instead of detecting the shell type dynamically.
Fixes#983Fixes#889
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
When git commands fail (e.g., not in a repo, invalid HEAD), git outputs
help text to stderr. Without explicit stdio option, execSync inherits
the parent's stdio causing help text to appear on terminal during
delegate_task execution.
Add stdio: ['pipe', 'pipe', 'pipe'] to capture stderr instead of
letting it leak to terminal.
- Added isModelCacheAvailable() to check if cache file exists
- Shows warning toast on session start if cache is missing
- Suggests running 'opencode models --refresh' or restarting
- Replace collector.register() with direct output.parts[textIndex].text modification
- All keyword types (ultrawork, search, analyze) now prepend to user message text
- Message format: keyword message + '---' separator + original text
- Update tests to verify text transformation instead of collector registration
- All 18 tests pass
Refresh documentation across all AGENTS.md files and update configuration documentation with latest features.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Apply consistent naming and small improvements to atlas, background-compaction, claude-code-hooks, and non-interactive-env hooks.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Add more keyword patterns for improved detection of work modes and triggers.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Rename agent parameter to subagent_type for consistency with delegate-task tool changes.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Add more comprehensive markdown-only file patterns for Prometheus planning agent. Extend test coverage for new patterns.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Multiple files were hardcoding ~/.config/opencode paths instead of using
getOpenCodeConfigDir() which respects the OPENCODE_CONFIG_DIR env var.
This broke profile isolation features like OCX ghost mode, where users
set OPENCODE_CONFIG_DIR to a custom path but oh-my-opencode.json and
other configs weren't being read from that location.
Changes:
- plugin-config.ts: Use getOpenCodeConfigDir() directly
- cli/doctor/checks: Use getOpenCodeConfigDir() for auth and config checks
- tools/lsp/config.ts: Use getOpenCodeConfigDir() for LSP config paths
- command loaders: Use getOpenCodeConfigDir() for global command dirs
- hooks: Use getOpenCodeConfigDir() for hook config paths
- config-path.ts: Mark getUserConfigDir() as deprecated
- tests: Ensure OPENCODE_CONFIG_DIR is properly isolated in tests
Anthropic's extended thinking error messages contain 'tool_use' and 'tool_result'
in the documentation URL text, causing incorrect detection as tool_result_missing
instead of thinking_block_order.
Fix: Check thinking_block_order BEFORE tool_result_missing.
- Rename agent name from 'atlas' to 'Atlas' (PascalCase like Sisyphus, Metis, Momus)
- Add migration for lowercase 'atlas' -> 'Atlas' for backward compatibility
- Keep hook name as 'atlas' (lowercase) to match other hook naming conventions
- Update all references in types, schema, hooks, commands, and tests
- Remove temperature from all categories
- Consolidate CATEGORY_MODEL_CATALOG into DEFAULT_CATEGORIES
- Replace 'general' and 'most-capable' with 'unspecified-low' and 'unspecified-high'
- Add Selection_Gate to unspecified categories to force deliberate selection
- Update quick category to use claude-haiku-4-5
- Update all references and tests across codebase
Update plugin handlers, commands, and integration points to use 'atlas' agent name. Start-work command and config handler now reference 'atlas'.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Hook name is now 'atlas' (not 'atlas-orchestrator'). Directory renamed to src/hooks/atlas/. All references updated.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
- Root AGENTS.md: Updated timestamp, commit hash, line counts
- src/agents/AGENTS.md: Updated to 50 lines, current structure
- src/cli/AGENTS.md: Updated to 57 lines, current structure
- src/features/AGENTS.md: Updated to 65 lines, current structure
- src/hooks/AGENTS.md: Updated to 53 lines, current structure
- src/shared/AGENTS.md: Updated to 52 lines, core utilities
- src/tools/AGENTS.md: Updated to 50 lines, tool categories
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Skip all keyword detection for background task sessions to prevent mode
injection (e.g., [analyze-mode], [search-mode]) which incorrectly triggers
Prometheus planner restrictions on Sisyphus sessions.
This aligns with the existing pattern used in:
- sisyphus-orchestrator (line 504)
- todo-continuation-enforcer (line 303)
- session-notification (line 278)
Closes#713
Add 5-second cooldown between continuation injections to prevent rapid-fire
session.idle events from causing infinite loop when boulder has incomplete tasks.
Bug: When switching from Prometheus to Sisyphus, the Prometheus ultrawork
template was still injected because:
1. setSessionAgent() only sets on first call, ignoring subsequent updates
2. keyword-detector relied solely on input.agent which could be stale
Fix:
- Use updateSessionAgent() instead of setSessionAgent() in index.ts
- keyword-detector now uses getSessionAgent() as primary source, fallback to input.agent
- Added tests for agent switch scenario
- Remove 'Start Sisyphus work session' text check, keep only <session-context> tag
- Update interactive_bash description with WARNING: TMUX ONLY emphasis
- Update tests to use <session-context> wrapper
OpenCode API returns different structures for user vs assistant messages:
- User: info.model = { providerID, modelID } (nested)
- Assistant: info.modelID, info.providerID (flat top-level)
Previous code only checked nested format, causing model info loss when
continuation hooks fired after assistant messages.
Files modified:
- todo-continuation-enforcer.ts
- ralph-loop/index.ts
- sisyphus-task/tools.ts
- background-agent/manager.ts
Added test for assistant message model extraction.
